为了改善船舶航行图像质量，准确分辨图像信息，提出基于视觉传达的船舶航行图像优化方法。利用双边滤波器与冲击滤波器处理模糊船舶航行图像，达到图像去噪、纹理平滑以及边缘特征增强的目的。根据模糊核的稀疏性特点，通过正则化交替迭代方式实现模糊最佳估计结果的确定后，基于梯度稀疏的反卷积方法实现模糊图像的复原，运用HSV色彩模型对复原后的船舶航行图像作优化处理，获得高质量船舶航行图像。实验结果表明，该方法可实现模糊船舶航行图像视觉传达优化，优化后图像的结构相似度、信息熵指标最高可达0.967、9.49，边缘强度、梯度均值、彩色熵指标达到设定要求，图像视觉优化效果突出。
In order to improve the quality of ship navigation images and accurately distinguish image information, a fuzzy ship navigation image optimization method based on visual communication is proposed. Using bilateral filters and impulse filters to process fuzzy ship navigation images, the goal of image denoising, texture smoothing, and edge feature enhancement is achieved. Based on the sparsity of the fuzzy kernel, the fuzzy optimal estimation result is determined through regularization alternating iteration, and the gradient sparse deconvolution method is used to restore the fuzzy image. The HSV color model is used to optimize the restored ship navigation image, Obtain high-quality ship navigation images. The experimental results show that this method can achieve visual communication optimization of fuzzy ship navigation images. After optimization, the structural similarity and information entropy indicators of the images can reach up to 0.967 and 9.49, and the edge strength, gradient mean, and color entropy indicators meet the set requirements. The visual optimization effect of the images is outstanding.
2023,45(19): 177-180 收稿日期：2023-02-23
DOI：10.3404/j.issn.1672-7649.2023.19.033
分类号：TP391
作者简介：张璐(1992-),女,硕士,讲师,研究方向为艺术设计、数字娱乐、造型基础及文创产品设计
参考文献：
[1] 关克平, 韩笑, 蒋宇. 基于TBD策略的船舶交通流视觉图像统计方法[J]. 上海海事大学学报, 2021, 42(2): 40-44+95.
GUAN Ke-ping, HAN Xiao, JIANG Yu. A visual image statistics method for ship traffic flow based on TBD strategy[J]. Journal of Shanghai Maritime University, 2021, 42(2): 40-44+95.
[2] 杨琼, 况姗芸, 冯义东. 基于全变差模型与卷积神经网络的模糊图像恢复[J]. 南京理工大学学报, 2022, 46(3): 277-283.
YANG Qiong, KUANG Shan-yun, FENG Yi-dong. Fuzzy image restoration based on TV model and CNN[J]. Journal of Nanjing University of Science and Technology, 2022, 46(3): 277-283.
[3] 周林宏, 杨戈, 李娜, 等. 基于自适应图像增强和图像去噪的水面航行船舶识别方法[J]. 船舶工程, 2021, 43(S2): 101-105.
ZHOU Lin-hong, YANG Ge, LI Na, et al. A Method for surface navigation ship recognition based on adaptive image enhancement and image denoising[J]. Ship Engineering, 2021, 43(S2): 101-105.
[4] 魏冬, 刘浩, 陈根龙, 等. 基于颜色校正和去模糊的水下图像增强方法[J]. 计算机科学, 2021, 48(4): 144-150.
WEI Dong, LIU Hao, CHEN Gen-long, et al. Underwater image enhancement based on color correction and deblurring[J]. Computer Science, 2021, 48(4): 144-150.
[5] 李博. 基于视觉传达的多帧图像高分辨率重建仿真[J]. 计算机仿真, 2021, 38(3): 113-116+121.
LI Bo. High resolution reconstruction simulation of multi-frame image based on visual communication[J]. Computer Simulation, 2021, 38(3): 113-116+121.
[6] 孙涛, 李东升. 基于非凸的全变分和低秩混合正则化的图像去模糊模型和算法[J]. 计算机学报, 2020, 43(4): 643-652.
SUN Tao, LI Dong-sheng. Nonconvex low-rank and total-variation regularized model and algorithm for image deblurring[J]. Chinese Journal of Computers, 2020, 43(4): 643-652.
